Timezone: »

 
Poster
Sublinear Time Orthogonal Tensor Decomposition
Zhao Song · David Woodruff · Huan Zhang

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #122
in Tuesday Posters »
A recent work (Wang et. al., NIPS 2015) gives the fastest known algorithms for orthogonal tensor decomposition with provable guarantees. Their algorithm is based on computing sketches of the input tensor, which requires reading the entire input. We show in a number of cases one can achieve the same theoretical guarantees in sublinear time, i.e., even without reading most of the input tensor. Instead of using sketches to estimate inner products in tensor decomposition algorithms, we use importance sampling. To achieve sublinear time, we need to know the norms of tensor slices, and we show how to do this in a number of important cases. For symmetric tensors $ T = \sum_{i=1}^k \lambda_i u_i^{\otimes p}$ with $\lambda_i > 0$ for all i, we estimate such norms in sublinear time whenever p is even. For the important case of p = 3 and small values of k, we can also estimate such norms. For asymmetric tensors sublinear time is not possible in general, but we show if the tensor slice norms are just slightly below $\| T \|_F$ then sublinear time is again possible. One of the main strengths of our work is empirical - in a number of cases our algorithm is orders of magnitude faster than existing methods with the same accuracy.
Keywords: Large Scale Learning and Big Data · (Other) Optimization · Component Analysis (ICA,PCA,CCA, FLDA)

Author Information

Zhao Song (UT-Austin)
David Woodruff (IBM Research)
Huan Zhang (UC-Davis)

More from the Same Authors